Add glob file type support (#8006)

* Replace FileType::Suffix with FileType::Glob

Suffix is rather limited and cannot be used to match files which have
semantic meaning based on location + file type (for example, Github
Action workflow files). This patch adds support for a Glob FileType to
replace Suffix, which encompasses the existing behavior & adds
additional file matching functionality.

Globs are standard Unix-style path globs, which are matched against the
absolute path of the file. If the configured glob for a language is a
relative glob (that is, it isn't an absolute path or already starts with
a glob pattern), a glob pattern will be prepended to allow matching
relative paths from any directory.

The order of file type matching is also updated to first match on globs
and then on extension. This is necessary as most cases where
glob-matching is useful will have already been matched by an extension
if glob matching is done last.

* Convert file-types suffixes to globs

* Use globs for filename matching

Trying to match the file-type raw strings against both filename and
extension leads to files with the same name as the extension having the
incorrect syntax.

* Match dockerfiles with suffixes

It's common practice to add a suffix to dockerfiles based on their
context, e.g. `Dockerfile.dev`, `Dockerfile.prod`, etc.

* Make env filetype matching more generic

Match on `.env` or any `.env.*` files.

* Update docs

* Use GlobSet to match all file type globs at once

* Update todo.txt glob patterns

* Consolidate language Configuration and Loader creation

This is a refactor that improves the error handling for creating
the `helix_core::syntax::Loader` from the default and user language
configuration.

* Fix integration tests

* Add additional starlark file-type glob

---------

Co-authored-by: Michael Davis <mcarsondavis@gmail.com>

Cargo.lock

@@ -1240,6 +1240,7 @@ dependencies = [
  "dunce",
  "encoding_rs",
  "etcetera",
+ "globset",
  "hashbrown 0.14.3",
  "helix-loader",
  "helix-stdx",

book/src/languages.md

@@ -78,24 +78,26 @@ from the above section. `file-types` is a list of strings or tables, for
 example:
 
 ```toml
-file-types = ["Makefile", "toml", { suffix = ".git/config" }]
+file-types = ["toml", { glob = "Makefile" }, { glob = ".git/config" }, { glob = ".github/workflows/*.yaml" } ]
 ```
 
 When determining a language configuration to use, Helix searches the file-types
 with the following priorities:
 
-1. Exact match: if the filename of a file is an exact match of a string in a
-   `file-types` list, that language wins. In the example above, `"Makefile"`
-   will match against `Makefile` files.
-2. Extension: if there are no exact matches, any `file-types` string that
-   matches the file extension of a given file wins. In the example above, the
-   `"toml"` matches files like `Cargo.toml` or `languages.toml`.
-3. Suffix: if there are still no matches, any values in `suffix` tables
-   are checked against the full path of the given file. In the example above,
-   the `{ suffix = ".git/config" }` would match against any `config` files
-   in `.git` directories. Note: `/` is used as the directory separator but is
-   replaced at runtime with the appropriate path separator for the operating
-   system, so this rule would match against `.git\config` files on Windows.
+1. Glob: values in `glob` tables are checked against the full path of the given
+   file. Globs are standard Unix-style path globs (e.g. the kind you use in Shell)
+   and can be used to match paths for a specific prefix, suffix, directory, etc.
+   In the above example, the `{ glob = "Makefile" }` config would match files
+   with the name `Makefile`, the `{ glob = ".git/config" }` config would match
+   `config` files in `.git` directories, and the `{ glob = ".github/workflows/*.yaml" }`
+   config would match any `yaml` files in `.github/workflow` directories. Note
+   that globs should always use the Unix path separator `/` even on Windows systems;
+   the matcher will automatically take the machine-specific separators into account.
+   If the glob isn't an absolute path or doesn't already start with a glob prefix,
+   `*/` will automatically be added to ensure it matches for any subdirectory.
+2. Extension: if there are no glob matches, any `file-types` string that matches
+   the file extension of a given file wins. In the example above, the `"toml"`
+   config matches files like `Cargo.toml` or `languages.toml`.
 
 ## Language Server configuration
 

helix-core/Cargo.toml

@@ -49,6 +49,7 @@ chrono = { version = "0.4", default-features = false, features = ["alloc", "std"
 
 etcetera = "0.8"
 textwrap = "0.16.0"
+globset = "0.4.14"
 
 nucleo.workspace = true
 parking_lot = "0.12"

helix-core/src/config.rs

@@ -1,10 +1,45 @@
-/// Syntax configuration loader based on built-in languages.toml.
-pub fn default_syntax_loader() -> crate::syntax::Configuration {
+use crate::syntax::{Configuration, Loader, LoaderError};
+
+/// Language configuration based on built-in languages.toml.
+pub fn default_lang_config() -> Configuration {
     helix_loader::config::default_lang_config()
         .try_into()
-        .expect("Could not serialize built-in languages.toml")
+        .expect("Could not deserialize built-in languages.toml")
 }
-/// Syntax configuration loader based on user configured languages.toml.
-pub fn user_syntax_loader() -> Result<crate::syntax::Configuration, toml::de::Error> {
+
+/// Language configuration loader based on built-in languages.toml.
+pub fn default_lang_loader() -> Loader {
+    Loader::new(default_lang_config()).expect("Could not compile loader for default config")
+}
+
+#[derive(Debug)]
+pub enum LanguageLoaderError {
+    DeserializeError(toml::de::Error),
+    LoaderError(LoaderError),
+}
+
+impl std::fmt::Display for LanguageLoaderError {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::DeserializeError(err) => write!(f, "Failed to parse language config: {err}"),
+            Self::LoaderError(err) => write!(f, "Failed to compile language config: {err}"),
+        }
+    }
+}
+
+impl std::error::Error for LanguageLoaderError {}
+
+/// Language configuration based on user configured languages.toml.
+pub fn user_lang_config() -> Result<Configuration, toml::de::Error> {
     helix_loader::config::user_lang_config()?.try_into()
 }
+
+/// Language configuration loader based on user configured languages.toml.
+pub fn user_lang_loader() -> Result<Loader, LanguageLoaderError> {
+    let config: Configuration = helix_loader::config::user_lang_config()
+        .map_err(LanguageLoaderError::DeserializeError)?
+        .try_into()
+        .map_err(LanguageLoaderError::DeserializeError)?;
+
+    Loader::new(config).map_err(LanguageLoaderError::LoaderError)
+}

helix-core/src/syntax.rs

@@ -82,12 +82,6 @@ pub struct Configuration {
     pub language_server: HashMap<String, LanguageServerConfiguration>,
 }
 
-impl Default for Configuration {
-    fn default() -> Self {
-        crate::config::default_syntax_loader()
-    }
-}
-
 // largely based on tree-sitter/cli/src/loader.rs
 #[derive(Debug, Serialize, Deserialize)]
 #[serde(rename_all = "kebab-case", deny_unknown_fields)]
@@ -164,9 +158,11 @@ pub enum FileType {
     /// The extension of the file, either the `Path::extension` or the full
     /// filename if the file does not have an extension.
     Extension(String),
-    /// The suffix of a file. This is compared to a given file's absolute
-    /// path, so it can be used to detect files based on their directories.
-    Suffix(String),
+    /// A Unix-style path glob. This is compared to the file's absolute path, so
+    /// it can be used to detect files based on their directories. If the glob
+    /// is not an absolute path and does not already start with a glob pattern,
+    /// a glob pattern will be prepended to it.
+    Glob(globset::Glob),
 }
 
 impl Serialize for FileType {
@@ -178,9 +174,9 @@ impl Serialize for FileType {
 
         match self {
             FileType::Extension(extension) => serializer.serialize_str(extension),
-            FileType::Suffix(suffix) => {
+            FileType::Glob(glob) => {
                 let mut map = serializer.serialize_map(Some(1))?;
-                map.serialize_entry("suffix", &suffix.replace(std::path::MAIN_SEPARATOR, "/"))?;
+                map.serialize_entry("glob", glob.glob())?;
                 map.end()
             }
         }
@@ -213,9 +209,20 @@ impl<'de> Deserialize<'de> for FileType {
                 M: serde::de::MapAccess<'de>,
             {
                 match map.next_entry::<String, String>()? {
-                    Some((key, suffix)) if key == "suffix" => Ok(FileType::Suffix({
-                        suffix.replace('/', std::path::MAIN_SEPARATOR_STR)
-                    })),
+                    Some((key, mut glob)) if key == "glob" => {
+                        // If the glob isn't an absolute path or already starts
+                        // with a glob pattern, add a leading glob so we
+                        // properly match relative paths.
+                        if !glob.starts_with('/') && !glob.starts_with("*/") {
+                            glob.insert_str(0, "*/");
+                        }
+
+                        globset::Glob::new(glob.as_str())
+                            .map(FileType::Glob)
+                            .map_err(|err| {
+                                serde::de::Error::custom(format!("invalid `glob` pattern: {}", err))
+                            })
+                    }
                     Some((key, _value)) => Err(serde::de::Error::custom(format!(
                         "unknown key in `file-types` list: {}",
                         key
@@ -752,6 +759,47 @@ pub struct SoftWrap {
     pub wrap_at_text_width: Option<bool>,
 }
 
+#[derive(Debug)]
+struct FileTypeGlob {
+    glob: globset::Glob,
+    language_id: usize,
+}
+
+impl FileTypeGlob {
+    fn new(glob: globset::Glob, language_id: usize) -> Self {
+        Self { glob, language_id }
+    }
+}
+
+#[derive(Debug)]
+struct FileTypeGlobMatcher {
+    matcher: globset::GlobSet,
+    file_types: Vec<FileTypeGlob>,
+}
+
+impl FileTypeGlobMatcher {
+    fn new(file_types: Vec<FileTypeGlob>) -> Result<Self, globset::Error> {
+        let mut builder = globset::GlobSetBuilder::new();
+        for file_type in &file_types {
+            builder.add(file_type.glob.clone());
+        }
+
+        Ok(Self {
+            matcher: builder.build()?,
+            file_types,
+        })
+    }
+
+    fn language_id_for_path(&self, path: &Path) -> Option<&usize> {
+        self.matcher
+            .matches(path)
+            .iter()
+            .filter_map(|idx| self.file_types.get(*idx))
+            .max_by_key(|file_type| file_type.glob.glob().len())
+            .map(|file_type| &file_type.language_id)
+    }
+}
+
 // Expose loader as Lazy<> global since it's always static?
 
 #[derive(Debug)]
@@ -759,7 +807,7 @@ pub struct Loader {
     // highlight_names ?
     language_configs: Vec<Arc<LanguageConfiguration>>,
     language_config_ids_by_extension: HashMap<String, usize>, // Vec<usize>
-    language_config_ids_by_suffix: HashMap<String, usize>,
+    language_config_ids_glob_matcher: FileTypeGlobMatcher,
     language_config_ids_by_shebang: HashMap<String, usize>,
 
     language_server_configs: HashMap<String, LanguageServerConfiguration>,
@@ -767,66 +815,57 @@ pub struct Loader {
     scopes: ArcSwap<Vec<String>>,
 }
 
+pub type LoaderError = globset::Error;
+
 impl Loader {
-    pub fn new(config: Configuration) -> Self {
-        let mut loader = Self {
-            language_configs: Vec::new(),
-            language_server_configs: config.language_server,
-            language_config_ids_by_extension: HashMap::new(),
-            language_config_ids_by_suffix: HashMap::new(),
-            language_config_ids_by_shebang: HashMap::new(),
-            scopes: ArcSwap::from_pointee(Vec::new()),
-        };
+    pub fn new(config: Configuration) -> Result<Self, LoaderError> {
+        let mut language_configs = Vec::new();
+        let mut language_config_ids_by_extension = HashMap::new();
+        let mut language_config_ids_by_shebang = HashMap::new();
+        let mut file_type_globs = Vec::new();
 
         for config in config.language {
             // get the next id
-            let language_id = loader.language_configs.len();
+            let language_id = language_configs.len();
 
             for file_type in &config.file_types {
                 // entry().or_insert(Vec::new).push(language_id);
                 match file_type {
-                    FileType::Extension(extension) => loader
-                        .language_config_ids_by_extension
-                        .insert(extension.clone(), language_id),
-                    FileType::Suffix(suffix) => loader
-                        .language_config_ids_by_suffix
-                        .insert(suffix.clone(), language_id),
+                    FileType::Extension(extension) => {
+                        language_config_ids_by_extension.insert(extension.clone(), language_id);
+                    }
+                    FileType::Glob(glob) => {
+                        file_type_globs.push(FileTypeGlob::new(glob.to_owned(), language_id));
+                    }
                 };
             }
             for shebang in &config.shebangs {
-                loader
-                    .language_config_ids_by_shebang
-                    .insert(shebang.clone(), language_id);
+                language_config_ids_by_shebang.insert(shebang.clone(), language_id);
             }
 
-            loader.language_configs.push(Arc::new(config));
+            language_configs.push(Arc::new(config));
         }
 
-        loader
+        Ok(Self {
+            language_configs,
+            language_config_ids_by_extension,
+            language_config_ids_glob_matcher: FileTypeGlobMatcher::new(file_type_globs)?,
+            language_config_ids_by_shebang,
+            language_server_configs: config.language_server,
+            scopes: ArcSwap::from_pointee(Vec::new()),
+        })
     }
 
     pub fn language_config_for_file_name(&self, path: &Path) -> Option<Arc<LanguageConfiguration>> {
         // Find all the language configurations that match this file name
         // or a suffix of the file name.
-        let configuration_id = path
-            .file_name()
-            .and_then(|n| n.to_str())
-            .and_then(|file_name| self.language_config_ids_by_extension.get(file_name))
+        let configuration_id = self
+            .language_config_ids_glob_matcher
+            .language_id_for_path(path)
             .or_else(|| {
                 path.extension()
                     .and_then(|extension| extension.to_str())
                     .and_then(|extension| self.language_config_ids_by_extension.get(extension))
-            })
-            .or_else(|| {
-                self.language_config_ids_by_suffix
-                    .iter()
-                    .find_map(|(file_type, id)| {
-                        if path.to_str()?.ends_with(file_type) {
-                            Some(id)
-                        } else {
-                            None
-                        }
-                    })
             });
 
         configuration_id.and_then(|&id| self.language_configs.get(id).cloned())
@@ -2592,7 +2631,8 @@ mod test {
         let loader = Loader::new(Configuration {
             language: vec![],
             language_server: HashMap::new(),
-        });
+        })
+        .unwrap();
         let language = get_language("rust").unwrap();
 
         let query = Query::new(language, query_str).unwrap();
@@ -2654,7 +2694,8 @@ mod test {
         let loader = Loader::new(Configuration {
             language: vec![],
             language_server: HashMap::new(),
-        });
+        })
+        .unwrap();
 
         let language = get_language("rust").unwrap();
         let config = HighlightConfiguration::new(
@@ -2760,7 +2801,8 @@ mod test {
         let loader = Loader::new(Configuration {
             language: vec![],
             language_server: HashMap::new(),
-        });
+        })
+        .unwrap();
         let language = get_language(language_name).unwrap();
 
         let config = HighlightConfiguration::new(language, "", "", "").unwrap();

helix-core/tests/indent.rs

@@ -186,7 +186,7 @@ fn test_treesitter_indent(
     lang_scope: &str,
     ignored_lines: Vec<std::ops::Range<usize>>,
 ) {
-    let loader = Loader::new(indent_tests_config());
+    let loader = Loader::new(indent_tests_config()).unwrap();
 
     // set runtime path so we can find the queries
     let mut runtime = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"));

helix-term/src/application.rs

@@ -96,11 +96,7 @@ fn setup_integration_logging() {
 }
 
 impl Application {
-    pub fn new(
-        args: Args,
-        config: Config,
-        syn_loader_conf: syntax::Configuration,
-    ) -> Result<Self, Error> {
+    pub fn new(args: Args, config: Config, lang_loader: syntax::Loader) -> Result<Self, Error> {
         #[cfg(feature = "integration")]
         setup_integration_logging();
 
@@ -126,7 +122,7 @@ impl Application {
             })
             .unwrap_or_else(|| theme_loader.default_theme(true_color));
 
-        let syn_loader = std::sync::Arc::new(syntax::Loader::new(syn_loader_conf));
+        let syn_loader = std::sync::Arc::new(lang_loader);
 
         #[cfg(not(feature = "integration"))]
         let backend = CrosstermBackend::new(stdout(), &config.editor);
@@ -394,10 +390,8 @@ impl Application {
 
     /// refresh language config after config change
     fn refresh_language_config(&mut self) -> Result<(), Error> {
-        let syntax_config = helix_core::config::user_syntax_loader()
-            .map_err(|err| anyhow::anyhow!("Failed to load language config: {}", err))?;
-
-        self.syn_loader = std::sync::Arc::new(syntax::Loader::new(syntax_config));
+        let lang_loader = helix_core::config::user_lang_loader()?;
+        self.syn_loader = std::sync::Arc::new(lang_loader);
         self.editor.syn_loader = self.syn_loader.clone();
         for document in self.editor.documents.values_mut() {
             document.detect_language(self.syn_loader.clone());

helix-term/src/health.rs

@@ -2,7 +2,7 @@ use crossterm::{
     style::{Color, Print, Stylize},
     tty::IsTty,
 };
-use helix_core::config::{default_syntax_loader, user_syntax_loader};
+use helix_core::config::{default_lang_config, user_lang_config};
 use helix_loader::grammar::load_runtime_file;
 use helix_view::clipboard::get_clipboard_provider;
 use std::io::Write;
@@ -128,7 +128,7 @@ pub fn languages_all() -> std::io::Result<()> {
     let stdout = std::io::stdout();
     let mut stdout = stdout.lock();
 
-    let mut syn_loader_conf = match user_syntax_loader() {
+    let mut syn_loader_conf = match user_lang_config() {
         Ok(conf) => conf,
         Err(err) => {
             let stderr = std::io::stderr();
@@ -141,7 +141,7 @@ pub fn languages_all() -> std::io::Result<()> {
                 err
             )?;
             writeln!(stderr, "{}", "Using default language config".yellow())?;
-            default_syntax_loader()
+            default_lang_config()
         }
     };
 
@@ -234,7 +234,7 @@ pub fn language(lang_str: String) -> std::io::Result<()> {
     let stdout = std::io::stdout();
     let mut stdout = stdout.lock();
 
-    let syn_loader_conf = match user_syntax_loader() {
+    let syn_loader_conf = match user_lang_config() {
         Ok(conf) => conf,
         Err(err) => {
             let stderr = std::io::stderr();
@@ -247,7 +247,7 @@ pub fn language(lang_str: String) -> std::io::Result<()> {
                 err
             )?;
             writeln!(stderr, "{}", "Using default language config".yellow())?;
-            default_syntax_loader()
+            default_lang_config()
         }
     };
 

helix-term/src/main.rs

@@ -145,18 +145,18 @@ FLAGS:
         }
     };
 
-    let syn_loader_conf = helix_core::config::user_syntax_loader().unwrap_or_else(|err| {
-        eprintln!("Bad language config: {}", err);
+    let lang_loader = helix_core::config::user_lang_loader().unwrap_or_else(|err| {
+        eprintln!("{}", err);
         eprintln!("Press <ENTER> to continue with default language config");
         use std::io::Read;
         // This waits for an enter press.
         let _ = std::io::stdin().read(&mut []);
-        helix_core::config::default_syntax_loader()
+        helix_core::config::default_lang_loader()
     });
 
     // TODO: use the thread local executor to spawn the application task separately from the work pool
-    let mut app = Application::new(args, config, syn_loader_conf)
-        .context("unable to create new application")?;
+    let mut app =
+        Application::new(args, config, lang_loader).context("unable to create new application")?;
 
     let exit_code = app.run(&mut EventStream::new()).await?;
 

helix-term/tests/test/commands/write.rs

@@ -315,7 +315,7 @@ async fn test_write_auto_format_fails_still_writes() -> anyhow::Result<()> {
     let mut app = helpers::AppBuilder::new()
         .with_file(file.path(), None)
         .with_input_text("#[l|]#et foo = 0;\n")
-        .with_lang_config(helpers::test_syntax_conf(Some(lang_conf.into())))
+        .with_lang_loader(helpers::test_syntax_loader(Some(lang_conf.into())))
         .build()?;
 
     test_key_sequences(&mut app, vec![(Some(":w<ret>"), None)], false).await?;

helix-term/tests/test/helpers.rs

@@ -139,7 +139,7 @@ pub async fn test_key_sequence_with_input_text<T: Into<TestCase>>(
     let test_case = test_case.into();
     let mut app = match app {
         Some(app) => app,
-        None => Application::new(Args::default(), test_config(), test_syntax_conf(None))?,
+        None => Application::new(Args::default(), test_config(), test_syntax_loader(None))?,
     };
 
     let (view, doc) = helix_view::current!(app.editor);
@@ -162,9 +162,9 @@ pub async fn test_key_sequence_with_input_text<T: Into<TestCase>>(
     .await
 }
 
-/// Generates language configs that merge in overrides, like a user language
+/// Generates language config loader that merge in overrides, like a user language
 /// config. The argument string must be a raw TOML document.
-pub fn test_syntax_conf(overrides: Option<String>) -> helix_core::syntax::Configuration {
+pub fn test_syntax_loader(overrides: Option<String>) -> helix_core::syntax::Loader {
     let mut lang = helix_loader::config::default_lang_config();
 
     if let Some(overrides) = overrides {
@@ -172,7 +172,7 @@ pub fn test_syntax_conf(overrides: Option<String>) -> helix_core::syntax::Config
         lang = helix_loader::merge_toml_values(lang, override_toml, 3);
     }
 
-    lang.try_into().unwrap()
+    helix_core::syntax::Loader::new(lang.try_into().unwrap()).unwrap()
 }
 
 /// Use this for very simple test cases where there is one input
@@ -271,7 +271,7 @@ pub fn new_readonly_tempfile() -> anyhow::Result<NamedTempFile> {
 pub struct AppBuilder {
     args: Args,
     config: Config,
-    syn_conf: helix_core::syntax::Configuration,
+    syn_loader: helix_core::syntax::Loader,
     input: Option<(String, Selection)>,
 }
 
@@ -280,7 +280,7 @@ impl Default for AppBuilder {
         Self {
             args: Args::default(),
             config: test_config(),
-            syn_conf: test_syntax_conf(None),
+            syn_loader: test_syntax_loader(None),
             input: None,
         }
     }
@@ -314,8 +314,8 @@ impl AppBuilder {
         self
     }
 
-    pub fn with_lang_config(mut self, syn_conf: helix_core::syntax::Configuration) -> Self {
-        self.syn_conf = syn_conf;
+    pub fn with_lang_loader(mut self, syn_loader: helix_core::syntax::Loader) -> Self {
+        self.syn_loader = syn_loader;
         self
     }
 
@@ -328,7 +328,7 @@ impl AppBuilder {
             bail!("Having the directory {path:?} in args.files[0] is not yet supported for integration tests");
         }
 
-        let mut app = Application::new(self.args, self.config, self.syn_conf)?;
+        let mut app = Application::new(self.args, self.config, self.syn_loader)?;
 
         if let Some((text, selection)) = self.input {
             let (view, doc) = helix_view::current!(app.editor);

languages.toml

@@ -253,7 +253,7 @@ source = { git = "https://github.com/FuelLabs/tree-sitter-sway", rev = "e491a005
 name = "toml"
 scope = "source.toml"
 injection-regex = "toml"
-file-types = ["toml", "poetry.lock", "Cargo.lock"]
+file-types = ["toml", { glob = "poetry.lock" }, { glob = "Cargo.lock" }]
 comment-token = "#"
 language-servers = [ "taplo" ]
 indent = { tab-width = 2, unit = "  " }
@@ -292,7 +292,7 @@ source = { git = "https://github.com/yusdacra/tree-sitter-protobuf", rev = "19c2
 name = "elixir"
 scope = "source.elixir"
 injection-regex = "(elixir|ex)"
-file-types = ["ex", "exs", "mix.lock"]
+file-types = ["ex", "exs", { glob = "mix.lock" }]
 shebangs = ["elixir"]
 roots = ["mix.exs", "mix.lock"]
 comment-token = "#"
@@ -361,20 +361,20 @@ file-types = [
   "geojson",
   "gltf",
   "webmanifest",
-  "flake.lock",
-  ".babelrc",
-  ".bowerrc",
-  ".jscrc",
+  { glob = "flake.lock" },
+  { glob = ".babelrc" },
+  { glob = ".bowerrc" },
+  { glob = ".jscrc" },
   "js.map",
   "ts.map",
   "css.map",
-  ".jslintrc",
+  { glob = ".jslintrc" },
   "jsonld",
-  ".vuerc",
-  "composer.lock",
-  ".watchmanconfig",
+  { glob = ".vuerc" },
+  { glob = "composer.lock" },
+  { glob = ".watchmanconfig" },
   "avsc",
-  ".prettierrc"
+  { glob = ".prettierrc" },
 ]
 language-servers = [ "vscode-json-language-server" ]
 auto-format = true
@@ -439,7 +439,7 @@ source = { git = "https://github.com/tree-sitter/tree-sitter-c", rev = "7175a6dd
 name = "cpp"
 scope = "source.cpp"
 injection-regex = "cpp"
-file-types = ["cc", "hh", "c++", "cpp", "hpp", "h", "ipp", "tpp", "cxx", "hxx", "ixx", "txx", "ino", "C", "H", "cu", "cuh", "cppm", "h++", "ii", "inl", { suffix = ".hpp.in" }, { suffix = ".h.in" }]
+file-types = ["cc", "hh", "c++", "cpp", "hpp", "h", "ipp", "tpp", "cxx", "hxx", "ixx", "txx", "ino", "C", "H", "cu", "cuh", "cppm", "h++", "ii", "inl", { glob = ".hpp.in" }, { glob = ".h.in" }]
 comment-token = "//"
 language-servers = [ "clangd" ]
 indent = { tab-width = 2, unit = "  " }
@@ -571,7 +571,7 @@ source = { git = "https://github.com/tree-sitter/tree-sitter-go", rev = "64457ea
 name = "gomod"
 scope = "source.gomod"
 injection-regex = "gomod"
-file-types = ["go.mod"]
+file-types = [{ glob = "go.mod" }]
 auto-format = true
 comment-token = "//"
 language-servers = [ "gopls" ]
@@ -598,7 +598,7 @@ source = { git = "https://github.com/dannylongeuay/tree-sitter-go-template", rev
 name = "gowork"
 scope = "source.gowork"
 injection-regex = "gowork"
-file-types = ["go.work"]
+file-types = [{ glob = "go.work" }]
 auto-format = true
 comment-token = "//"
 language-servers = [ "gopls" ]
@@ -613,7 +613,7 @@ name = "javascript"
 scope = "source.js"
 injection-regex = "(js|javascript)"
 language-id = "javascript"
-file-types = ["js", "mjs", "cjs", "rules", "es6", "pac", "jakefile"]
+file-types = ["js", "mjs", "cjs", "rules", "es6", "pac", { glob = "jakefile" }]
 shebangs = ["node"]
 comment-token = "//"
 language-servers = [ "typescript-language-server" ]
@@ -716,7 +716,7 @@ source = { git = "https://github.com/tree-sitter/tree-sitter-html", rev = "29f53
 name = "python"
 scope = "source.python"
 injection-regex = "python"
-file-types = ["py","pyi","py3","pyw","ptl",".pythonstartup",".pythonrc","SConstruct", "rpy", "cpy", "ipy", "pyt", "SConscript"]
+file-types = ["py", "pyi", "py3", "pyw", "ptl", "rpy", "cpy", "ipy", "pyt", { glob = ".pythonstartup" }, { glob = ".pythonrc" }, { glob = "SConstruct" }, { glob = "SConscript" }]
 shebangs = ["python"]
 roots = ["pyproject.toml", "setup.py", "poetry.lock", "pyrightconfig.json"]
 comment-token = "#"
@@ -769,38 +769,38 @@ injection-regex = "ruby"
 file-types = [
   "rb",
   "rake",
-  "rakefile",
   "irb",
-  "gemfile",
   "gemspec",
-  "Rakefile",
-  "Gemfile",
   "rabl",
   "jbuilder",
   "jb",
-  "Podfile",
   "podspec",
-  "Vagrantfile",
-  "Brewfile",
   "rjs",
   "rbi",
-  "Guardfile",
-  "Capfile",
-  "Cheffile",
-  "Hobofile",
-  "Appraisals",
-  "Rantfile",
-  "Berksfile",
-  "Berksfile.lock",
-  "Thorfile",
-  "Puppetfile",
-  "Fastfile",
-  "Appfile",
-  "Deliverfile",
-  "Matchfile",
-  "Scanfile",
-  "Snapfile",
-  "Gymfile"
+  { glob = "rakefile" },
+  { glob = "gemfile" },
+  { glob = "Rakefile" },
+  { glob = "Gemfile" },
+  { glob = "Podfile" },
+  { glob = "Vagrantfile" },
+  { glob = "Brewfile" },
+  { glob = "Guardfile" },
+  { glob = "Capfile" },
+  { glob = "Cheffile" },
+  { glob = "Hobofile" },
+  { glob = "Appraisals" },
+  { glob = "Rantfile" },
+  { glob = "Berksfile" },
+  { glob = "Berksfile.lock" },
+  { glob = "Thorfile" },
+  { glob = "Puppetfile" },
+  { glob = "Fastfile" },
+  { glob = "Appfile" },
+  { glob = "Deliverfile" },
+  { glob = "Matchfile" },
+  { glob = "Scanfile" },
+  { glob = "Snapfile" },
+  { glob = "Gymfile" },
 ]
 shebangs = ["ruby"]
 comment-token = "#"
@@ -819,43 +819,43 @@ file-types = [
   "sh",
   "bash",
   "zsh",
-  ".bash_history",
-  ".bash_login",
-  ".bash_logout",
-  ".bash_profile",
-  ".bashrc",
-  ".profile",
-  ".zshenv",
   "zshenv",
-  ".zlogin",
   "zlogin",
-  ".zlogout",
   "zlogout",
-  ".zprofile",
   "zprofile",
-  ".zshrc",
   "zshrc",
-  ".zimrc",
-  "APKBUILD",
-  "PKGBUILD",
   "eclass",
   "ebuild",
   "bazelrc",
-  ".bash_aliases",
   "Renviron",
-  ".Renviron",
-  ".xprofile",
-  ".xsession",
-  ".xsessionrc",
   "zsh-theme",
   "ksh",
   "cshrc",
   "tcshrc",
-  ".yashrc",
-  ".yash_profile",
-  ".hushlogin",
   "bashrc_Apple_Terminal",
-  "zshrc_Apple_Terminal"
+  "zshrc_Apple_Terminal",
+  { glob = ".bash_history" },
+  { glob = ".bash_login" },
+  { glob = ".bash_logout" },
+  { glob = ".bash_profile" },
+  { glob = ".bashrc" },
+  { glob = ".profile" },
+  { glob = ".zshenv" },
+  { glob = ".zlogin" },
+  { glob = ".zlogout" },
+  { glob = ".zprofile" },
+  { glob = ".zshrc" },
+  { glob = ".zimrc" },
+  { glob = "APKBUILD" },
+  { glob = "PKGBUILD" },
+  { glob = ".bash_aliases" },
+  { glob = ".Renviron" },
+  { glob = ".xprofile" },
+  { glob = ".xsession" },
+  { glob = ".xsessionrc" },
+  { glob = ".yashrc" },
+  { glob = ".yash_profile" },
+  { glob = ".hushlogin" },
 ]
 shebangs = ["sh", "bash", "dash", "zsh"]
 comment-token = "#"
@@ -1216,7 +1216,7 @@ source = { git = "https://github.com/the-mikedavis/tree-sitter-tsq", rev = "48b5
 [[language]]
 name = "cmake"
 scope = "source.cmake"
-file-types = ["cmake", "CMakeLists.txt"]
+file-types = ["cmake", { glob = "CMakeLists.txt" }]
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
 language-servers = [ "cmake-language-server" ]
@@ -1229,7 +1229,7 @@ source = { git = "https://github.com/uyha/tree-sitter-cmake", rev = "6e51463ef30
 [[language]]
 name = "make"
 scope = "source.make"
-file-types = ["Makefile", "makefile", "make", "mk", "mak", "GNUmakefile", "OCamlMakefile"]
+file-types = [{ glob = "Makefile" }, { glob = "makefile" }, "make", "mk", "mak", {glob = "GNUmakefile" }, { glob = "OCamlMakefile" }]
 shebangs = ["make", "gmake"]
 injection-regex = "(make|makefile|Makefile|mk)"
 comment-token = "#"
@@ -1372,7 +1372,7 @@ source = { git = "https://github.com/Flakebi/tree-sitter-tablegen", rev = "568dd
 name = "markdown"
 scope = "source.md"
 injection-regex = "md|markdown"
-file-types = ["md", "markdown", "PULLREQ_EDITMSG", "mkd", "mdwn", "mdown", "markdn", "mdtxt", "mdtext", "workbook"]
+file-types = ["md", "markdown", "mkd", "mdwn", "mdown", "markdn", "mdtxt", "mdtext", "workbook", { glob = "PULLREQ_EDITMSG" }]
 roots = [".marksman.toml"]
 language-servers = [ "marksman" ]
 indent = { tab-width = 2, unit = "  " }
@@ -1424,7 +1424,7 @@ name = "dockerfile"
 scope = "source.dockerfile"
 injection-regex = "docker|dockerfile"
 roots = ["Dockerfile", "Containerfile"]
-file-types = ["Dockerfile", "dockerfile", "Containerfile", "containerfile"]
+file-types = [{ glob = "Dockerfile*" }, { glob = "dockerfile*" }, { glob = "Containerfile*" }, { glob = "containerfile*" }]
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
 language-servers = [ "docker-langserver" ]
@@ -1436,7 +1436,7 @@ source = { git = "https://github.com/camdencheek/tree-sitter-dockerfile", rev =
 [[language]]
 name = "git-commit"
 scope = "git.commitmsg"
-file-types = ["COMMIT_EDITMSG"]
+file-types = [{ glob = "COMMIT_EDITMSG" }]
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
 rulers = [51, 73]
@@ -1461,7 +1461,7 @@ source = { git = "https://github.com/the-mikedavis/tree-sitter-diff", rev = "fd7
 [[language]]
 name = "git-rebase"
 scope = "source.gitrebase"
-file-types = ["git-rebase-todo"]
+file-types = [{ glob = "git-rebase-todo" }]
 injection-regex = "git-rebase"
 comment-token = "#"
 indent = { tab-width = 2, unit = "y" }
@@ -1474,7 +1474,7 @@ source = { git = "https://github.com/the-mikedavis/tree-sitter-git-rebase", rev
 name = "regex"
 scope = "source.regex"
 injection-regex = "regex"
-file-types = ["regex", ".Rbuildignore"]
+file-types = ["regex", { glob = ".Rbuildignore" }]
 
 [[grammar]]
 name = "regex"
@@ -1483,7 +1483,7 @@ source = { git = "https://github.com/tree-sitter/tree-sitter-regex", rev = "e1cf
 [[language]]
 name = "git-config"
 scope = "source.gitconfig"
-file-types = [".gitmodules", ".gitconfig", { suffix = ".git/config" }, { suffix = ".config/git/config" }]
+file-types = [{ glob = ".gitmodules" }, { glob = ".gitconfig" }, { glob = ".git/config" }, { glob = ".config/git/config" }]
 injection-regex = "git-config"
 comment-token = "#"
 indent = { tab-width = 4, unit = "\t" }
@@ -1495,7 +1495,7 @@ source = { git = "https://github.com/the-mikedavis/tree-sitter-git-config", rev
 [[language]]
 name = "git-attributes"
 scope = "source.gitattributes"
-file-types = [".gitattributes"]
+file-types = [{ glob = ".gitattributes" }]
 injection-regex = "git-attributes"
 comment-token = "#"
 grammar = "gitattributes"
@@ -1507,7 +1507,7 @@ source = { git = "https://github.com/mtoohey31/tree-sitter-gitattributes", rev =
 [[language]]
 name = "git-ignore"
 scope = "source.gitignore"
-file-types = [".gitignore", ".gitignore_global", ".ignore", ".prettierignore", ".eslintignore", ".npmignore", "CODEOWNERS", { suffix = ".config/helix/ignore" }, { suffix = ".helix/ignore" }]
+file-types = [{ glob = ".gitignore" }, { glob = ".gitignore_global" }, { glob = ".ignore" }, { glob = ".prettierignore" }, { glob = ".eslintignore" }, { glob = ".npmignore"}, { glob = "CODEOWNERS" }, { glob = ".config/helix/ignore" }, { glob = ".helix/ignore" }]
 injection-regex = "git-ignore"
 comment-token = "#"
 grammar = "gitignore"
@@ -1572,7 +1572,7 @@ source = { git = "https://github.com/jaredramirez/tree-sitter-rescript", rev = "
 name = "erlang"
 scope = "source.erlang"
 injection-regex = "erl(ang)?"
-file-types = ["erl", "hrl", "app", "rebar.config", "rebar.lock"]
+file-types = ["erl", "hrl", "app", { glob = "rebar.config" }, { glob = "rebar.lock" }]
 roots = ["rebar.config"]
 shebangs = ["escript"]
 comment-token = "%%"
@@ -1698,7 +1698,7 @@ source = { git = "https://github.com/Hubro/tree-sitter-robot", rev = "322e4cc657
 name = "r"
 scope = "source.r"
 injection-regex = "(r|R)"
-file-types = ["r", "R", ".Rprofile", "Rprofile.site", ".RHistory"]
+file-types = ["r", "R", { glob = ".Rprofile" }, { glob = "Rprofile.site" }, { glob = ".RHistory" }]
 shebangs = ["r", "R"]
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
@@ -1913,7 +1913,7 @@ source = { git = "https://github.com/ap29600/tree-sitter-odin", rev = "b219207e4
 name = "meson"
 scope = "source.meson"
 injection-regex = "meson"
-file-types = ["meson.build", "meson_options.txt"]
+file-types = [{ glob = "meson.build" }, { glob = "meson_options.txt" }]
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
 
@@ -1924,7 +1924,7 @@ source = { git = "https://github.com/staysail/tree-sitter-meson", rev = "32a83e8
 [[language]]
 name = "sshclientconfig"
 scope = "source.sshclientconfig"
-file-types = [{ suffix = ".ssh/config" }, { suffix = "/etc/ssh/ssh_config" }]
+file-types = [{ glob = ".ssh/config" }, { glob = "/etc/ssh/ssh_config" }]
 comment-token = "#"
 
 [[grammar]]
@@ -2045,7 +2045,7 @@ source = { git = "https://github.com/sogaiu/tree-sitter-clojure", rev = "e57c569
 name = "starlark"
 scope = "source.starlark"
 injection-regex = "(starlark|bzl|bazel)"
-file-types = ["bzl", "bazel", "BUILD", "star"]
+file-types = ["bzl", "bazel", "star", { glob = "BUILD" }, { glob = "BUILD.*" }]
 comment-token = "#"
 indent = { tab-width = 4, unit = "    " }
 grammar = "python"
@@ -2413,7 +2413,7 @@ source = { git = "https://github.com/hh9527/tree-sitter-wit", rev = "c917790ab9a
 [[language]]
 name = "env"
 scope = "source.env"
-file-types = [".env", ".env.local", ".env.development", ".env.production", ".env.dist", ".envrc", ".envrc.local", ".envrc.private"]
+file-types = [{ glob = ".env" }, { glob = ".env.*" }, { glob = ".envrc" }, { glob = ".envrc.*" }]
 injection-regex = "env"
 comment-token = "#"
 indent = { tab-width = 4, unit = "\t" }
@@ -2441,7 +2441,7 @@ file-types = [
   "volume",
   "kube",
   "network",
-  ".editorconfig",
+  { glob = ".editorconfig" },
   "properties",
   "cfg",
   "directory"
@@ -2569,7 +2569,7 @@ source = { git = "https://github.com/mtoohey31/tree-sitter-pem", rev = "be67a433
 [[language]]
 name = "passwd"
 scope = "source.passwd"
-file-types = ["passwd"]
+file-types = [{ glob = "passwd" }]
 
 [[grammar]]
 name = "passwd"
@@ -2578,7 +2578,7 @@ source = { git = "https://github.com/ath3/tree-sitter-passwd", rev = "20239395ea
 [[language]]
 name = "hosts"
 scope = "source.hosts"
-file-types = ["hosts"]
+file-types = [{ glob = "hosts" }]
 comment-token = "#"
 
 [[grammar]]
@@ -2786,7 +2786,7 @@ source = { git = "https://github.com/lefp/tree-sitter-opencl", rev = "8e1d24a570
 [[language]]
 name = "just"
 scope = "source.just"
-file-types = ["justfile", "Justfile", ".justfile", ".Justfile"]
+file-types = [{ glob = "justfile" }, { glob = "Justfile" }, { glob = ".justfile" }, { glob = ".Justfile" }]
 injection-regex = "just"
 comment-token = "#"
 indent = { tab-width = 4, unit = "\t" }
@@ -2945,7 +2945,7 @@ source = { git = "https://github.com/kylegoetz/tree-sitter-unison", rev = "1f505
 [[language]]
 name = "todotxt"
 scope = "text.todotxt"
-file-types = [{ suffix = ".todo.txt" }, "todotxt"]
+file-types = [{ glob = "todo.txt" }, { glob = "*.todo.txt" }, "todotxt"]
 formatter = { command = "sort" }
 auto-format = true